tcp/dccp: remove twchain

TCP listener refactoring, part 3 :

Our goal is to hash SYN_RECV sockets into main ehash for fast lookup,
and parallel SYN processing.

Current inet_ehash_bucket contains two chains, one for ESTABLISH (and
friend states) sockets, another for TIME_WAIT sockets only.

As the hash table is sized to get at most one socket per bucket, it
makes little sense to have separate twchain, as it makes the lookup
slightly more complicated, and doubles hash table memory usage.

If we make sure all socket types have the lookup keys at the same
offsets, we can use a generic and faster lookup. It turns out TIME_WAIT
and ESTABLISHED sockets already have common lookup fields for IPv4.

[ INET_TW_MATCH() is no longer needed ]

I'll provide a follow-up to factorize IPv6 lookup as well, to remove
INET6_TW_MATCH()

This way, SYN_RECV pseudo sockets will be supported the same.

A new sock_gen_put() helper is added, doing either a sock_put() or
inet_twsk_put() [ and will support SYN_RECV later ].

Note this helper should only be called in real slow path, when rcu
lookup found a socket that was moved to another identity (freed/reused
immediately), but could eventually be used in other contexts, like
sock_edemux()

Before patch :

dmesg | grep "TCP established"

TCP established hash table entries: 524288 (order: 11, 8388608 bytes)

After patch :

TCP established hash table entries: 524288 (order: 10, 4194304 bytes)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 13 insertions, 70 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5d6b1a609da8..e4695dde1af6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2194,18 +2194,6 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
 
-static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
-{
-	return hlist_nulls_empty(head) ? NULL :
-		list_entry(head->first, struct inet_timewait_sock, tw_node);
-}
-
-static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
-{
-	return !is_a_nulls(tw->tw_node.next) ?
-		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
-}
-
 /*
  * Get next listener socket follow cur.  If cur is NULL, get first socket
  * starting from bucket given in st->bucket; when st->bucket is zero the
@@ -2309,10 +2297,9 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 	return rc;
 }
 
-static inline bool empty_bucket(struct tcp_iter_state *st)
+static inline bool empty_bucket(const struct tcp_iter_state *st)
 {
-	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
-		hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain);
 }
 
 /*
@@ -2329,7 +2316,6 @@ static void *established_get_first(struct seq_file *seq)
 	for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
 		struct sock *sk;
 		struct hlist_nulls_node *node;
-		struct inet_timewait_sock *tw;
 		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
 
 		/* Lockless fast path for the common case of empty buckets */
@@ -2345,18 +2331,7 @@ static void *established_get_first(struct seq_file *seq)
 			rc = sk;
 			goto out;
 		}
-		st->state = TCP_SEQ_STATE_TIME_WAIT;
-		inet_twsk_for_each(tw, node,
-				   &tcp_hashinfo.ehash[st->bucket].twchain) {
-			if (tw->tw_family != st->family ||
-			    !net_eq(twsk_net(tw), net)) {
-				continue;
-			}
-			rc = tw;
-			goto out;
-		}
 		spin_unlock_bh(lock);
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
 	}
 out:
 	return rc;
@@ -2365,7 +2340,6 @@ out:
 static void *established_get_next(struct seq_file *seq, void *cur)
 {
 	struct sock *sk = cur;
-	struct inet_timewait_sock *tw;
 	struct hlist_nulls_node *node;
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
@@ -2373,45 +2347,16 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 	++st->num;
 	++st->offset;
 
-	if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
-		tw = cur;
-		tw = tw_next(tw);
-get_tw:
-		while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
-			tw = tw_next(tw);
-		}
-		if (tw) {
-			cur = tw;
-			goto out;
-		}
-		spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
-
-		/* Look for next non empty bucket */
-		st->offset = 0;
-		while (++st->bucket <= tcp_hashinfo.ehash_mask &&
-				empty_bucket(st))
-			;
-		if (st->bucket > tcp_hashinfo.ehash_mask)
-			return NULL;
-
-		spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
-	} else
-		sk = sk_nulls_next(sk);
+	sk = sk_nulls_next(sk);
 
 	sk_nulls_for_each_from(sk, node) {
 		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
-			goto found;
+			return sk;
 	}
 
-	st->state = TCP_SEQ_STATE_TIME_WAIT;
-	tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
-	goto get_tw;
-found:
-	cur = sk;
-out:
-	return cur;
+	spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+	++st->bucket;
+	return established_get_first(seq);
 }
 
 static void *established_get_idx(struct seq_file *seq, loff_t pos)
@@ -2464,10 +2409,9 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 		if (rc)
 			break;
 		st->bucket = 0;
+		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		/* Fallthrough */
 	case TCP_SEQ_STATE_ESTABLISHED:
-	case TCP_SEQ_STATE_TIME_WAIT:
-		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		if (st->bucket > tcp_hashinfo.ehash_mask)
 			break;
 		rc = established_get_first(seq);
@@ -2524,7 +2468,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 		}
 		break;
 	case TCP_SEQ_STATE_ESTABLISHED:
-	case TCP_SEQ_STATE_TIME_WAIT:
 		rc = established_get_next(seq, v);
 		break;
 	}
@@ -2548,7 +2491,6 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 		if (v != SEQ_START_TOKEN)
 			spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
 		break;
-	case TCP_SEQ_STATE_TIME_WAIT:
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
 			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
@@ -2707,6 +2649,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 static int tcp4_seq_show(struct seq_file *seq, void *v)
 {
 	struct tcp_iter_state *st;
+	struct sock *sk = v;
 	int len;
 
 	if (v == SEQ_START_TOKEN) {
@@ -2721,14 +2664,14 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
 	switch (st->state) {
 	case TCP_SEQ_STATE_LISTENING:
 	case TCP_SEQ_STATE_ESTABLISHED:
-		get_tcp4_sock(v, seq, st->num, &len);
+		if (sk->sk_state == TCP_TIME_WAIT)
+			get_timewait4_sock(v, seq, st->num, &len);
+		else
+			get_tcp4_sock(v, seq, st->num, &len);
 		break;
 	case TCP_SEQ_STATE_OPENREQ:
 		get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
 		break;
-	case TCP_SEQ_STATE_TIME_WAIT:
-		get_timewait4_sock(v, seq, st->num, &len);
-		break;
 	}
 	seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
 out: